{"id":"https://openalex.org/W7212064516","doi":"https://doi.org/10.48550/arxiv.2609.06873","title":"Large Classification-Risk-Optional Label Acquisition","display_name":"Large Classification-Risk-Optional Label Acquisition","publication_year":2026,"publication_date":"2026-09-06","ids":{"openalex":"https://openalex.org/W7212064516","doi":"https://doi.org/10.48550/arxiv.2609.06873"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.06873","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.06873","pdf_url":"https://arxiv.org/pdf/2609.06873","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.06873","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5150970607","display_name":"F. Setoudehtanzangi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Setoudehtanzangi, F.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057375178","display_name":"Geoffrey John McLachlan","orcid":"https://orcid.org/0000-0002-5921-3145","observed_orcids":["https://orcid.org/0000-0002-5921-3145"]},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"McLachlan, Geoffrey J.","raw_affiliation_strings":["School of Mathematics and Physics , The University of Queensland , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics , The University of Queensland , Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.6259999871253967},{"id":"https://openalex.org/keywords/label-acquisition","display_name":"label acquisition","score":0.878000020980835},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"multi-class classification","score":0.7739999890327454},{"id":"https://openalex.org/keywords/fisher-information","display_name":"Fisher information","score":0.843999981880188},{"id":"https://openalex.org/keywords/two-stage-adaptive-design","display_name":"two-stage adaptive design","score":0.5879999995231628},{"id":"https://openalex.org/keywords/gaussian-discriminant-analysis","display_name":"Gaussian discriminant analysis","score":0.953000009059906},{"id":"https://openalex.org/keywords/entropy-sampling","display_name":"entropy sampling","score":0.4059999883174896},{"id":"https://openalex.org/keywords/margin-sampling","display_name":"margin sampling","score":0.9359999895095825}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5019999742507935},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.4560999870300293},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.44339999556541443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3894999921321869},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.3723999857902527},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35409998893737793},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3402000069618225},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.2524000108242035},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.06873","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.06873","pdf_url":"https://arxiv.org/pdf/2609.06873","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.06873","doi":"https://doi.org/10.48550/arxiv.2609.06873","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.06873","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.06873","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.06873","pdf_url":"https://arxiv.org/pdf/2609.06873","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212064516.pdf","grobid_xml":"https://content.openalex.org/works/W7212064516.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1513874326","https://openalex.org/W1807095418","https://openalex.org/W2021367230","https://openalex.org/W2104848109","https://openalex.org/W2596535828","https://openalex.org/W2904739162","https://openalex.org/W3032338640","https://openalex.org/W4213328897","https://openalex.org/W4300031234","https://openalex.org/W4309394632","https://openalex.org/W6888909630","https://openalex.org/W7133193895","https://openalex.org/W7204274953","https://openalex.org/W7204905954"],"related_works":["https://openalex.org/W7203775799","https://openalex.org/W7213517206","https://openalex.org/W2116938621","https://openalex.org/W1905087629","https://openalex.org/W2112683085","https://openalex.org/W7100375271","https://openalex.org/W194089216","https://openalex.org/W3033860060","https://openalex.org/W7095933524","https://openalex.org/W2964075712"],"abstract_inverted_index":{"We":[0,16,106,140],"study":[1],"how":[2,79],"a":[3,75,143],"limited":[4],"labeling":[5,211,234],"budget":[6,235],"should":[7],"be":[8,34],"allocated":[9],"to":[10,78,98,175],"minimize":[11],"multiclass":[12,52,68],"zero-one":[13],"classification":[14,19,130],"risk.":[15,70],"consider":[17],"parametric":[18],"problems":[20],"in":[21],"which":[22],"features":[23],"are":[24],"observed":[25],"for":[26,160],"all":[27],"sampling":[28,223],"units":[29],"while":[30,172],"class":[31],"labels":[32],"can":[33,132,186],"acquired":[35,45],"selectively.":[36],"By":[37],"combining":[38],"the":[39,48,62,90,108,149,168,176,194,210,227,233],"Fisher":[40,207],"information":[41,82,104],"supplied":[42],"by":[43],"an":[44,57,173],"label":[46,76],"with":[47,85],"local":[49],"geometry":[50],"of":[51,66],"excess":[53,69],"risk,":[54],"we":[55],"derive":[56,117],"acquisition":[58,110,138,170,185,192],"criterion":[59,152],"that":[60,88,126,147,183],"minimizes":[61],"leading":[63],"asymptotic":[64],"coefficient":[65],"expected":[67],"The":[71,197],"resulting":[72,169],"rule":[73],"values":[74],"according":[77,97],"strongly":[80],"its":[81,113],"is":[83],"aligned":[84],"parameter":[86,103],"directions":[87],"perturb":[89],"active":[91],"Bayes":[92],"decision":[93],"boundary,":[94],"rather":[95],"than":[96,205],"posterior":[99,127],"uncertainty":[100,128],"or":[101,221],"global":[102],"alone.":[105],"characterize":[107],"oracle":[109,150],"design,":[111],"establish":[112],"threshold":[114],"structure,":[115],"and":[116,119,129,135,156,193,224],"face-specific":[118],"cost-sensitive":[120],"extensions.":[121],"An":[122],"analytic":[123],"example":[124],"shows":[125,182],"value":[131],"produce":[133],"different,":[134],"even":[136],"reversed,":[137],"rankings.":[139],"further":[141],"develop":[142],"two-stage":[144],"adaptive":[145,198],"procedure":[146],"attains":[148,201],"leading-risk":[151],"under":[153],"regularity":[154],"conditions":[155],"provide":[157],"explicit":[158],"results":[159],"Gaussian":[161],"discriminant":[162],"analysis.":[163],"Three-class":[164],"QDA":[165],"experiments":[166],"illustrate":[167],"geometry,":[171],"application":[174],"six-class":[177],"Statlog":[178],"Landsat":[179],"Satellite":[180],"data":[181],"classification-risk":[184,199],"differ":[187],"materially":[188],"from":[189],"both":[190],"uncertainty-based":[191],"complete-classification-information":[195],"comparator.":[196],"design":[200],"lower":[202],"mean":[203],"error":[204],"this":[206],"comparator":[208],"across":[209],"budgets":[212],"considered,":[213],"although":[214],"it":[215],"does":[216],"not":[217],"uniformly":[218],"outperform":[219],"entropy":[220],"margin":[222],"differences":[225],"among":[226],"targeted":[228],"strategies":[229],"become":[230],"small":[231],"as":[232],"increases.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-10T00:00:00"}